Stop Searching. Start Trusting.

The curated directory of MCP servers, vetted for security, efficiency, and quality.

Browse DirectoryWhy Us?

Tired of the MCP "Marketplace" Chaos?

We built MCPScout.ai to solve the ecosystems biggest pain points.

No Insecure Dumps

We manually analyze every server for basic security flaws.

Easy Setup

Our gotcha notes warn you about complex setups.

Avoid "Token Hogs"

We estimate token costs for cost-effective agents.

Products, Not Demos

We filter out "Hello World" demos.

CATEGORIES:
SORT:

Vetted Servers(9120)

0
0
High Cost
jph2 icon
Sec6

A Model Context Protocol (MCP) server for basic Universal Scene Description (USD) operations and NVIDIA Omniverse integration.

Setup Requirements

  • ⚠️Requires Pixar USD ('pxr') Python bindings, which can be complex to install and might need specific system configurations or pre-built binaries.
  • ⚠️The project is explicitly marked as 'WARNING totally WIP!!!' and 'not working in any meaningful way!!!' in the README, indicating it is not production-ready and may be unstable.
  • ⚠️Python 3.7+ is required.
Review RequiredView Analysis
The server allows direct file path manipulation for creating, opening, saving, and analyzing USD stages. If exposed to untrusted clients with broad file system permissions, this could lead to directory traversal, arbitrary file creation/overwrites, or resource exhaustion attacks. The project's README explicitly states it's 'totally WIP' and 'needs ~20 hours of polish (tests, CI, error handling) to meet enterprise standards,' indicating security is not yet mature. No obvious 'eval' or hardcoded secrets were found.
Updated: 2025-12-17GitHub→
0
0
High Cost
HaolongChen icon

playwright-mcp-vercel

by HaolongChen

Sec3

Provides a REST API endpoint to proxy requests to the Playwright Model Context Protocol (MCP) tool, enabling serverless browser automation.

Setup Requirements

  • ⚠️Requires a Vercel account for serverless deployment.
  • ⚠️During cold starts in the serverless environment, `npx playwright-mcp` will likely download `playwright-mcp` and potentially Playwright browser binaries, leading to increased latency and resource consumption.
  • ⚠️The `package.json` specifies `main: "index.js"` and `start: "node index.js"`, but the provided server logic is in `server.js` and Vercel configuration explicitly points to `server.js` for deployment. This discrepancy could cause confusion for local development if `index.js` is a wrapper file not provided.
Review RequiredView Analysis
The server directly proxies arbitrary JSON payloads to the `playwright-mcp` tool via an unauthenticated API endpoint (`/mcp`). Crucially, the `server.js` code lacks input validation for the incoming MCP payload, which the `README` explicitly recommends as a security consideration. This allows any caller to execute arbitrary browser automation commands, potentially leading to malicious actions (e.g., unauthorized scraping, resource exhaustion, interaction with sensitive web services if the server has network access). Using `spawn` with `shell: true` can introduce shell injection risks, although in this specific case, the command (`npx playwright-mcp`) is static and user input is passed via stdin, reducing the immediate risk from command construction itself. Without authentication and robust input validation, this server is not safe for public exposure.
Updated: 2025-12-12GitHub→
0
0
Medium Cost
felixtrz icon

iwsdk-rag-mcp

by felixtrz

Sec8

Provides a Model Context Protocol (MCP) server for AI assistants to perform semantic code search and understand the Immersive Web SDK (IWSDK) codebase using Retrieval-Augmented Generation (RAG) with vector embeddings.

Setup Requirements

  • ⚠️Requires Node.js version 20.19.0 or higher.
  • ⚠️pnpm is the recommended package manager for installation and development.
  • ⚠️The first run involves downloading a ~420MB embedding model (`jinaai/jina-embeddings-v2-base-code`) from Hugging Face, which can cause a slow initial startup.
  • ⚠️This is an MCP server designed for integration with tools like Claude Code/Desktop, not a standalone web service.
Verified SafeView Analysis
The ingestion pipeline uses `child_process.execSync` to clone the Immersive Web SDK repository from a hardcoded trusted URL (facebook/immersive-web-sdk) and to install/build its dependencies. While these commands are executed in a controlled build environment, any compromise of the IWSDK repository or its dependencies could theoretically lead to arbitrary code execution during the ingestion phase. The live server itself does not expose these powerful functionalities to external input. The embedding model is downloaded from Hugging Face on first run, from a specified and generally trusted model source (`jinaai/jina-embeddings-v2-base-code`). No hardcoded secrets or arbitrary `eval` usage were found.
Updated: 2026-01-16GitHub→
0
0
Low Cost
JeanmarcoLujan icon

MCP-Server-y-SAP-B1

by JeanmarcoLujan

Sec3

Acts as a Smart Connector for SAP Business One (B1) by exposing a subset of its data via the Model Context Protocol (MCP), enabling integration with AI models or other MCP-compatible clients.

Setup Requirements

  • ⚠️Requires an active SAP HANA database instance with specified schema and valid credentials.
  • ⚠️Environment variables (HANA_HOST, HANA_PORT, HANA_USER, HANA_PASSWORD, HANA_DB_SCHEMA) must be configured for the application to connect to SAP HANA.
  • ⚠️The server is designed to be consumed by a Model Context Protocol (MCP) client or an LLM, not a generic HTTP client, requiring specific client-side integration.
Review RequiredView Analysis
CRITICAL: Hardcoded SAP HANA database credentials (username and password) found in 'test-hana.js'. This file should not contain sensitive information, especially if it could be accidentally deployed. CRITICAL: 'sslValidateCertificate' is set to 'FALSE' for SAP HANA connections in both the test file and the main HanaService, disabling essential SSL/TLS certificate validation. This makes the database connection highly vulnerable to Man-in-the-Middle (MITM) attacks and should be 'TRUE' in production. Positive: Uses environment variables for main service configuration, and parameterized queries in B1QueryService to prevent SQL injection. The SAP_SCHEMA whitelist is a good security practice for controlled data access.
Updated: 2025-12-01GitHub→
0
0
High Cost
sanjanb icon

mcp-agent

by sanjanb

Sec9

A production-ready HR Assistant that answers HR policy questions using RAG, performs resume screening, and tracks onboarding tasks.

Setup Requirements

  • ⚠️Requires OpenAI or Gemini API Key (Paid) for AI responses, otherwise falls back to basic retrieval.
  • ⚠️Requires Streamlit for the user interface.
  • ⚠️Optional: Redis server for conversation caching; otherwise, an in-memory fallback is used.
  • ⚠️Python 3.8+ required.
  • ⚠️Embedding models (e.g., 'all-MiniLM-L6-v2') are downloaded on first use, which may cause an initial delay.
Verified SafeView Analysis
API keys are consistently retrieved from environment variables, which is good practice. Tool functions are called directly (no 'eval' or similar dynamic code execution). File handling for PDFs and text seems robust, relying on established libraries. The onboarding tool uses a threading lock for atomic JSON file writes, improving data integrity. Minor note on `sys.path.append` which is common in Python project setups but could pose a risk if the root path were untrusted. Overall, the project demonstrates a strong focus on secure coding practices.
Updated: 2025-12-03GitHub→
0
0
Low Cost

mcp-server-demo

by Mukuloli

Sec6

A demonstration server application, likely written in Python, showcasing a specific protocol or service (possibly related to 'MCP').

Setup Requirements

  • ⚠️Requires `uv` installed to manage dependencies and run the server.
  • ⚠️Requires a specific Python version, as indicated by the `.python-version` file.
Verified SafeView Analysis
Cannot perform a thorough security audit without access to the `main.py` file content. The project appears to be a standard Python application; however, without code review, potential risks like 'eval' usage, insecure network handling, or unvalidated inputs cannot be assessed. Assumed generic demo server without explicit red flags.
Updated: 2025-11-18GitHub→
0
0
Medium Cost
freddyfredster icon
Sec9

This repository demonstrates how to refactor, optimize, and govern Power BI semantic models using natural language prompts via GitHub Copilot and the Power BI Modeling MCP Server VS Code extension.

Setup Requirements

  • ⚠️Requires GitHub Copilot subscription (Paid)
  • ⚠️Requires Power BI Desktop with 'Modern metadata ON' enabled
  • ⚠️Requires Power BI Modeling MCP Server VS Code extension
Verified SafeView Analysis
The provided source code primarily consists of documentation, Power BI report/model configuration files (PBIP format), and prompt examples. There are no executable scripts, server-side code, 'eval' statements, obfuscation, or hardcoded secrets within the truncated code. The 'Power BI Modeling MCP Server' itself is a VS Code extension, whose internal source code is not provided in this repository for audit. The security score reflects the benign nature of the provided repository content, not the external components it leverages.
Updated: 2025-12-01GitHub→
0
0
High Cost
mgrandau icon

telescope-mcp

by mgrandau

Sec8

An MCP (Model Context Protocol) server enabling AI agents to control telescope hardware (cameras, motors, sensors) and providing a web dashboard for human monitoring and manual control.

Setup Requirements

  • ⚠️Requires ZWO ASI SDK (`libASICamera2.so`) for hardware camera control (Linux/macOS specific paths and udev rules for permissions).
  • ⚠️Requires `gh` (GitHub CLI) to be installed and authenticated for issue creation utilities (`utils/create_issues.py`).
  • ⚠️Python 3.10+ is required.
  • ⚠️The `pdm` package manager is used consistently across the project for dependency management and running scripts.
  • ⚠️PySerial is implicitly required for Arduino sensor and serial motor drivers (hardware mode).
Verified SafeView Analysis
The project uses `subprocess.run` (in `utils/create_issues.py` for `gh` CLI, and `utils/analyze_mcp_overhead.py` for querying other MCP servers). For `create_issues.py`, `tempfile.NamedTemporaryFile` and input validation (`DANGEROUS_CHARS_REGEX`) are used to mitigate shell injection risks, which is a good practice. The `gh` CLI itself relies on external authentication setup. The web dashboard (`web/app.py`) can be exposed to the network (`0.0.0.0:8080`) if `--dashboard-host 0.0.0.0` is used, requiring external firewalling for production. No obvious hardcoded secrets or 'eval' usage.
Updated: 2026-01-05GitHub→
0
0
Medium Cost
chayan-1906 icon
Sec3

Enables AI agents to perform complex browser automation and web scraping using Puppeteer, managing persistent sessions and various interaction modes.

Setup Requirements

  • ⚠️Requires Node.js 18+.
  • ⚠️Relies on a direct GitHub dependency (`mcp-utils`) which could be unstable or change.
  • ⚠️Creates persistent user profiles (e.g., `~/.browser-automation-mcp`) that grow over time.
Review RequiredView Analysis
The server uses `eval()` with user-provided script in the `execute-script` tool, which allows arbitrary JavaScript execution within the browser context, posing a significant security risk for data exfiltration or malicious actions if untrusted input is processed. Additionally, `app.use(cors())` enables Cross-Origin Resource Sharing for all origins, making the server vulnerable to requests from any domain, potentially leading to unauthorized control or data access. Persistent browser profiles can also store sensitive session data in the user's home directory.
Updated: 2025-12-05GitHub→
0
0
Medium Cost
johnlam1968 icon

ibkr_headless_mcp

by johnlam1968

Sec9

Provides an MCP server to access Interactive Brokers (IBKR) API endpoints for financial data and trading operations via an LLM agent, using OAuth for authentication.

Setup Requirements

  • ⚠️Requires an Interactive Brokers (IBKR) account with API access enabled.
  • ⚠️Requires generation and secure local storage of OAuth 1.0a private key files (`private_encryption.pem`, `private_signature.pem`) and a DH prime, as detailed in the `ibind` library's OAuth wiki.
  • ⚠️Requires manual configuration of multiple IBKR OAuth credentials and file paths in a `.env` file.
Verified SafeView Analysis
The server correctly externalizes sensitive IBKR OAuth credentials into environment variables and separate files. There are no obvious 'eval' or 'exec' calls within the provided source code, reducing direct code injection risks. The primary security consideration is the potential for an unconstrained LLM agent to make unauthorized data retrieval requests through the `call_endpoint` tool, as it directly passes agent-provided `path` and `params` to the `ibind` client's GET method. However, since `call_endpoint` exclusively uses `client.get` and the documented endpoints are read-only, the risk of malicious write operations (e.g., placing trades) appears mitigated by the current implementation which is restricted to GET requests.
Updated: 2026-01-07GitHub→
0
0
High Cost
support-and-care-labs icon

mail-mcp

by support-and-care-labs

Sec8

Serves as an MCP server to access, search, and analyze Apache Maven mailing list archives, extracting metadata and providing structured access to email content and threads.

Setup Requirements

  • ⚠️Docker Desktop (or Podman) with Docker Compose V2 is required to run the full stack.
  • ⚠️An Elasticsearch instance must be running and accessible for data storage and search.
  • ⚠️Mailing list archives (mbox files) need to be downloaded and indexed into Elasticsearch using provided CLI tools before the server can return meaningful results.
Verified SafeView Analysis
The source code does not contain obvious direct injection vulnerabilities (e.g., `eval()` on user input) or hardcoded secrets. Elasticsearch queries are constructed using structured Python dictionaries, which generally mitigates injection risks. Network requests to external APIs (`lists.apache.org`) use `httpx` with timeouts. The `docker-compose.yml` disables Elasticsearch security (`xpack.security.enabled=false`) for development, which is a significant configuration risk for production environments but not a vulnerability in the application's source code itself. The server binds to `0.0.0.0` by default, requiring external network security if deployed beyond a local/private network.
Updated: 2025-12-21GitHub→
0
0
Low Cost
Ragtimelab icon

mcp-manager

by Ragtimelab

Sec8

A command-line interface (CLI) tool for managing Model Context Protocol (MCP) servers locally, providing installation, upgrade, health check, backup, and diagnostic functionalities similar to `brew`.

Setup Requirements

  • ⚠️Requires Python 3.10+.
  • ⚠️Relies on `uv` for installation and local execution.
  • ⚠️Requires `uvx` and/or `npx` to be installed and in PATH for managing respective MCP server types (Python/Node.js).
Verified SafeView Analysis
The tool directly executes `uvx`, `npx`, and `npm` via subprocess calls. While this is its core function for managing packages, it inherently relies on the security of these underlying tools and the trustworthiness of the package names provided by the user. No direct `eval` or obfuscation found. Sensitive environment variables are masked in `show_server` output. Configuration is stored locally in `~/.claude.json`.
Updated: 2025-12-05GitHub→
PreviousPage 452 of 760Next